SlideShare a Scribd company logo
1 of 17
Download to read offline
Adversarial Image Attacks
By Koshin Khodiyar
linkedin.com/in/koshin-khodiyar-2a79311b2/
Contents ● What is are
Adversarial Image
Attacks?
● Adversarial examples
● Nightshade
What is Machine
Learning?
Artificial
Intelligence
Machine
Learning
REF:
https://www.geeksforgeeks.org/artificial-neural-networks-and-its-applications/
● Machine Learning is a subset of Artificial
Intelligence, where a machine learns for
itself
● A neural network is a series of
interconnected nodes that work to
produce a specified output from an input
How Machine
Learning Works
REF: Confidence-Guided-Open-World [Li et al]
● A neural network is trained on
labelled data and can practice
classifying the image with feedback
● It is then tested against images it
hasn’t seen before
● If the neural network is trained on the
training data too much it will start to
overfit, and when given test data will
not necessarily give accurate results
What is an Adversarial
Image Attack?
● Purposefully causing a ML model to produce mispredictions
when identifying data
● There are 3 main fields:
○ Image recognition
○ Natural language
○ Auditory processing
● As a field it is relatively new as it has only been around since
2013
REF:
Making an Invisibility Cloak: Real World Adversarial Attacks on Object
Detectors [Wu et al]
https://arxiv.org/abs/1312.6199
What does an Adversarial Image Attack look like?
● This image of a panda has been identified,
the model gives confidence limits on the
categories it has identified. These represent
the probability that the respective category
has been found in the image
● It has identified the giant panda and has put a
box around it in the image
What does an Adversarial Image Attack look like?
REF: https://openai.com/research/attacking-machine-learning-with-adversarial-examples
There are some slight differences between these two pictures, e.g the right one is fuzzier. This is
because the right image has had an adversarial attack performed on it, while the left image is the
original.
What does an Adversarial Image Attack look like?
REF: https://openai.com/research/attacking-machine-learning-with-adversarial-examples
The image is fuzzier due to a layer of noise that has been layered onto it. This causes the panda to be misclassified as a gibbon
Panda Gibbon
A Brief Overview
This shows a simplified
model of how the
network classifies
pandas and gibbons.
When the adversarial
attack is performed the
image of the panda
moves across the line
making it appear to the
neural network as a
gibbon.
REF: https://www.youtube.com/watch?v=i1sp4X57TL4
Adversarial Patch - Tom Brown
Adversarial attacks can be
very powerful, altering one
pixel or even creating a patch.
The video shows how a
banana can be misclassified
as a toaster in real time just
by adding in the patch.
Real World Example: Stop Sign
REF: Robust Physical-World Attacks on
Deep Learning Models [Ekyholt et al]
Researchers in Michigan placed
small pieces of tape on this stop
sign which caused the model to
misclassify it as a 45 mph speed
limit sign.
When this technology is used in the
real world it has the potential to go
wrong very drastically.
Adversarial Examples
REF: Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors [Wu et al]
The adversarial attack varies in
effectiveness, due to a variety of
factors, a small rotation or slight
illumination. Can cause the attack to
stop working.
The man is wearing an adversarial
patch as a jumper. This stops him
being recognised by the image
recognition network. However in a
slightly different environment, his is
recognised and identified.
Nightshade: a Defensive use
Nightshade was created as a way for artists to protect
their work from being used as data to train image
generation models on. It was created by Ben Zhao at the
university of Chicago.
Nightshade: a Defensive use
Nightshade works by adding imperceptible noise to
images during the training process, making them more
robust to adversarial attacks.
When an image is used without permission it poisons
the network. Causing the generated images to
become distorted. As more poisoned images are used
the image becomes unrecognisable.
Nightshade can be found here:
https://nightshade.cs.uchicago.edu/userguide.html
Ethical Considerations
● Regulation and oversight
● Privacy Breaches
● Data protection
● Transparency
Further Reading
2018
Threat of Adversarial Attacks on
Deep learning in Computer
Vision: A Survey
2021
Advances in Adversarial Attacks and
Defenses in Computer Vision: A
Survey
2021
Hacking AI: Security & Privacy of
Machine Learning Models
?
Black Box
X Y
2020
A Survey of Black-Box Adversarial
Attacks on Computer Vision
Models
Interesting Papers
linkedin.com/in/koshin-khodiyar-2a79311b2/

More Related Content

Similar to Presentation about adversarial image attacks

GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxRMDAcademicCoordinat
 
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...Exploring The Potential of Generative Adversarial Network: A Comparative Stud...
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...IRJET Journal
 
A Neural Network Approach to Deep-Fake Video Detection
A Neural Network Approach to Deep-Fake Video DetectionA Neural Network Approach to Deep-Fake Video Detection
A Neural Network Approach to Deep-Fake Video DetectionIRJET Journal
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learningAntonio Rueda-Toicen
 
Generative Adversarial Networks GANs.pdf
Generative Adversarial Networks GANs.pdfGenerative Adversarial Networks GANs.pdf
Generative Adversarial Networks GANs.pdfMatthewHaws4
 
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...StampedeCon
 
Deep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic ApplicationsDeep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic ApplicationsDarius Burschka
 
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...EnriqueLlerenaDomngu
 
Generative Adversarial Networks for machine learning and data scienece.docx
Generative Adversarial Networks for machine learning and data scienece.docxGenerative Adversarial Networks for machine learning and data scienece.docx
Generative Adversarial Networks for machine learning and data scienece.docx18527TRIVENBABU
 
Magic ai these are the optical illusions that trick, fool, and flummox compu...
Magic ai  these are the optical illusions that trick, fool, and flummox compu...Magic ai  these are the optical illusions that trick, fool, and flummox compu...
Magic ai these are the optical illusions that trick, fool, and flummox compu...sean22
 
introduction to deeplearning
introduction to deeplearningintroduction to deeplearning
introduction to deeplearningEyad Alshami
 
IRJET - Direct Me-Nevigation for Blind People
IRJET -  	  Direct Me-Nevigation for Blind PeopleIRJET -  	  Direct Me-Nevigation for Blind People
IRJET - Direct Me-Nevigation for Blind PeopleIRJET Journal
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdfssuser07e9f2
 
Il deep learning ed una nuova generazione di AI - Simone Scardapane
Il deep learning ed una nuova generazione di AI - Simone ScardapaneIl deep learning ed una nuova generazione di AI - Simone Scardapane
Il deep learning ed una nuova generazione di AI - Simone ScardapaneData Driven Innovation
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptxAndleebFatima16
 
A Survey on Security and Privacy of Machine Learning
A Survey on Security and Privacy of Machine LearningA Survey on Security and Privacy of Machine Learning
A Survey on Security and Privacy of Machine LearningThang Dang Duy
 
Neural network image recognition
Neural network image recognitionNeural network image recognition
Neural network image recognitionOleksii Sekundant
 

Similar to Presentation about adversarial image attacks (20)

GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
 
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...Exploring The Potential of Generative Adversarial Network: A Comparative Stud...
Exploring The Potential of Generative Adversarial Network: A Comparative Stud...
 
A Neural Network Approach to Deep-Fake Video Detection
A Neural Network Approach to Deep-Fake Video DetectionA Neural Network Approach to Deep-Fake Video Detection
A Neural Network Approach to Deep-Fake Video Detection
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
Generative Adversarial Networks GANs.pdf
Generative Adversarial Networks GANs.pdfGenerative Adversarial Networks GANs.pdf
Generative Adversarial Networks GANs.pdf
 
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
 
Deep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic ApplicationsDeep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic Applications
 
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...
Prototyping of a Robot Arm Controller: getting the hands dirty to learn new t...
 
Generative Adversarial Networks for machine learning and data scienece.docx
Generative Adversarial Networks for machine learning and data scienece.docxGenerative Adversarial Networks for machine learning and data scienece.docx
Generative Adversarial Networks for machine learning and data scienece.docx
 
Magic ai these are the optical illusions that trick, fool, and flummox compu...
Magic ai  these are the optical illusions that trick, fool, and flummox compu...Magic ai  these are the optical illusions that trick, fool, and flummox compu...
Magic ai these are the optical illusions that trick, fool, and flummox compu...
 
The age of GANs
The age of GANsThe age of GANs
The age of GANs
 
introduction to deeplearning
introduction to deeplearningintroduction to deeplearning
introduction to deeplearning
 
IRJET - Direct Me-Nevigation for Blind People
IRJET -  	  Direct Me-Nevigation for Blind PeopleIRJET -  	  Direct Me-Nevigation for Blind People
IRJET - Direct Me-Nevigation for Blind People
 
Generative models
Generative modelsGenerative models
Generative models
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdf
 
Il deep learning ed una nuova generazione di AI - Simone Scardapane
Il deep learning ed una nuova generazione di AI - Simone ScardapaneIl deep learning ed una nuova generazione di AI - Simone Scardapane
Il deep learning ed una nuova generazione di AI - Simone Scardapane
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
 
A Survey on Security and Privacy of Machine Learning
A Survey on Security and Privacy of Machine LearningA Survey on Security and Privacy of Machine Learning
A Survey on Security and Privacy of Machine Learning
 
Neural network image recognition
Neural network image recognitionNeural network image recognition
Neural network image recognition
 

Recently uploaded

Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10ROLANARIBATO3
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantadityabhardwaj282
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxFarihaAbdulRasheed
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsHajira Mahmood
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRlizamodels9
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024AyushiRastogi48
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsCharlene Llagas
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxEran Akiva Sinbar
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxmalonesandreagweneth
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxNandakishor Bhaurao Deshmukh
 
Transposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptTransposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptArshadWarsi13
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |aasikanpl
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PPRINCE C P
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett SquareIsiahStephanRadaza
 

Recently uploaded (20)

Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are important
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutions
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of Traits
 
Engler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomyEngler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomy
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
 
Transposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.pptTransposable elements in prokaryotes.ppt
Transposable elements in prokaryotes.ppt
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C P
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett Square
 

Presentation about adversarial image attacks

  • 1. Adversarial Image Attacks By Koshin Khodiyar linkedin.com/in/koshin-khodiyar-2a79311b2/
  • 2. Contents ● What is are Adversarial Image Attacks? ● Adversarial examples ● Nightshade
  • 3. What is Machine Learning? Artificial Intelligence Machine Learning REF: https://www.geeksforgeeks.org/artificial-neural-networks-and-its-applications/ ● Machine Learning is a subset of Artificial Intelligence, where a machine learns for itself ● A neural network is a series of interconnected nodes that work to produce a specified output from an input
  • 4. How Machine Learning Works REF: Confidence-Guided-Open-World [Li et al] ● A neural network is trained on labelled data and can practice classifying the image with feedback ● It is then tested against images it hasn’t seen before ● If the neural network is trained on the training data too much it will start to overfit, and when given test data will not necessarily give accurate results
  • 5. What is an Adversarial Image Attack? ● Purposefully causing a ML model to produce mispredictions when identifying data ● There are 3 main fields: ○ Image recognition ○ Natural language ○ Auditory processing ● As a field it is relatively new as it has only been around since 2013 REF: Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors [Wu et al] https://arxiv.org/abs/1312.6199
  • 6. What does an Adversarial Image Attack look like? ● This image of a panda has been identified, the model gives confidence limits on the categories it has identified. These represent the probability that the respective category has been found in the image ● It has identified the giant panda and has put a box around it in the image
  • 7. What does an Adversarial Image Attack look like? REF: https://openai.com/research/attacking-machine-learning-with-adversarial-examples There are some slight differences between these two pictures, e.g the right one is fuzzier. This is because the right image has had an adversarial attack performed on it, while the left image is the original.
  • 8. What does an Adversarial Image Attack look like? REF: https://openai.com/research/attacking-machine-learning-with-adversarial-examples The image is fuzzier due to a layer of noise that has been layered onto it. This causes the panda to be misclassified as a gibbon
  • 9. Panda Gibbon A Brief Overview This shows a simplified model of how the network classifies pandas and gibbons. When the adversarial attack is performed the image of the panda moves across the line making it appear to the neural network as a gibbon.
  • 10. REF: https://www.youtube.com/watch?v=i1sp4X57TL4 Adversarial Patch - Tom Brown Adversarial attacks can be very powerful, altering one pixel or even creating a patch. The video shows how a banana can be misclassified as a toaster in real time just by adding in the patch.
  • 11. Real World Example: Stop Sign REF: Robust Physical-World Attacks on Deep Learning Models [Ekyholt et al] Researchers in Michigan placed small pieces of tape on this stop sign which caused the model to misclassify it as a 45 mph speed limit sign. When this technology is used in the real world it has the potential to go wrong very drastically.
  • 12. Adversarial Examples REF: Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors [Wu et al] The adversarial attack varies in effectiveness, due to a variety of factors, a small rotation or slight illumination. Can cause the attack to stop working. The man is wearing an adversarial patch as a jumper. This stops him being recognised by the image recognition network. However in a slightly different environment, his is recognised and identified.
  • 13. Nightshade: a Defensive use Nightshade was created as a way for artists to protect their work from being used as data to train image generation models on. It was created by Ben Zhao at the university of Chicago.
  • 14. Nightshade: a Defensive use Nightshade works by adding imperceptible noise to images during the training process, making them more robust to adversarial attacks. When an image is used without permission it poisons the network. Causing the generated images to become distorted. As more poisoned images are used the image becomes unrecognisable. Nightshade can be found here: https://nightshade.cs.uchicago.edu/userguide.html
  • 15. Ethical Considerations ● Regulation and oversight ● Privacy Breaches ● Data protection ● Transparency
  • 16. Further Reading 2018 Threat of Adversarial Attacks on Deep learning in Computer Vision: A Survey 2021 Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey 2021 Hacking AI: Security & Privacy of Machine Learning Models ? Black Box X Y 2020 A Survey of Black-Box Adversarial Attacks on Computer Vision Models Interesting Papers